检索结果-南通市图书馆

Fast target-aware learning for few-shot video object segmentation

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2022年第8期65卷 71-86页

作者： Yadang CHEN Chuanyan HAO Zhi-Xin YANG Enhua WU Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and Technology School of Education Science and Technology Nanjing University of Posts and Telecommunications State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of Macau State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of Sciences Faculty of Science and Technology University of Macau

Few-shot video object segmentation(FSVOS) aims to segment a specific object throughout a video sequence when only the first-frame annotation is given. In this study, we develop a fast target-aware learning approach for FSVOS, where the proposed approach adapts to new video sequences from its firstframe annotation through a lightweight procedure. The proposed network comprises two models. First, the meta knowledge model learns the general semantic features for the input video image and up-samples the coarse predicted mask to the original image size. Second, the target model adapts quickly from the limited support set. Concretely, during the online inference for testing the video, we first employ fast optimization techniques to train a powerful target model by minimizing the segmentation error in the first frame and then use it to predict the subsequent frames. During the offline training, we use a bilevel-optimization strategy to mimic the full testing procedure to train the meta knowledge model across multiple video *** proposed method is trained only on an individual public video object segmentation(VOS) benchmark without additional training sets and compared favorably with state-of-the-art methods on DAVIS-2017, with a J &F overall score of 71.6%, and on YouT ubeVOS-2018, with a J &F overall score of 75.4%. Meanwhile,a high inference speed of approximately 0.13 s per frame is maintained.

关键词： video object segmentation few-shot target-aware meta knowledge bilevel-optimization

Scribble-Supervised video object segmentation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 339-353页

作者： Peiliang Huang Junwei Han Nian Liu Jun Ren Dingwen Zhang Brain and Artificial Intelligence Laboratory School of AutomationNorthwestern Polytechnical UniversityXi’an 710072China IEEE Department of Engagement Services Mohamed Bin Zayed University of Artificial IntelligenceAbuDhabiUnited Arab Emirate Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory BeijingChina

Recently,video object segmentation has received great attention in the computer vision *** of the existing methods heavily rely on the pixel-wise human annotations,which are expensive and time-consuming to *** tackle this problem,we make an early attempt to achieve video object segmentation with scribble-level supervision,which can alleviate large amounts of human labor for collecting the manual ***,using conventional network architectures and learning objective functions under this scenario cannot work well as the supervision information is highly sparse and *** address this issue,this paper introduces two novel elements to learn the video object segmentation *** first one is the scribble attention module,which captures more accurate context information and learns an effective attention map to enhance the contrast between foreground and *** other one is the scribble-supervised loss,which can optimize the unlabeled pixels and dynamically correct inaccurate segmented areas during the training *** evaluate the proposed method,we implement experiments on two video object segmentation benchmark datasets,You Tube-video object segmentation(VOS),and densely annotated video segmentation(DAVIS)-*** first generate the scribble annotations from the original per-pixel ***,we train our model and compare its test performance with the baseline models and other existing *** experiments demonstrate that the proposed method can work effectively and approach to the methods requiring the dense per-pixel annotations.

关键词： Convolutional neural networks(CNNs) scribble self-attention video object segmentation weakly supervised

维普期刊数据库

Research on video motion object segmentation for content-based application

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai University(English Edition) 2006年第2期10卷 142-143页

作者：包红强 ZHANG Zhao- yang YU Song-yu WANG Suo-zhong WANG Nu-li FANG Yong WANG Zhi-gang School of Communication and Information Engineering Shanghai University Shanghai 200072 P. R. China Shanghai University Shanghai Jiaotong University Shanghai Institute of Technical Physics Chinese Academy of Sviences Shanghai Astronautics Bureau

With the development of the modern information society, more and more multimedia information is available. So the technology of multimedia processing is becoming the important task for the irrelevant area of scientist. Among of the multimedia, the visual informarion is more attractive due to its direct, vivid characteristic, but at the same rime the huge amount of video data causes many challenges if the video storage, processing and transmission.

关键词： image processing video object segmentation spatiotemporal framework MPEG-4.

维普期刊数据库

video segmentation using multiple features based on EM algorithm

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Engineering and Electronics 2004年第4期15卷 656-662页

作者： ZhangFengchao YangJie LiuErqi InstituteofImageProcessingandPatternRecognition ShanghaiJiaotongUniversityShanghai200030P.R.China TheSecondAcademy ChinaAerospaceofScienceandIndustryCorporationBeijing100854P.R.China

object-based video segmentation is an important issue for many multimedia applications. A video segmentation method based on EM algorithm is proposed. We consider video segmentation as an unsupervised classification problem and apply EM algorithm to obtain the maximum-likelihood estimation of the Gaussian model parameters for model-based segmentation. We simultaneously combine multiple features (motion, color) within a maximum likelihood framework to obtain accurate segment results. We also use the temporal consistency among video frames to improve the speed of EM algorithm. Experimental results on typical MPEG-4 sequences and real scene sequences show that our method has an attractive accuracy and robustness.

关键词： EM algorithm maximum-likelihood estimation video object segmentation

objective Performance Evaluation of video segmentation Algorithms with Ground-Truth

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Shanghai University(English Edition) 2004年第1期8卷 70-74页

作者：杨高波张兆扬 Schol of Communication and Information Engineering Shanghai University Shanghai 200072 P.R. China

While the development of particular video segmentation algorithms has attracted considerable research interest, relatively little effort has been devoted to provide a methodology for evaluating their performance. In this paper, we propose a methodology to objectively evaluate video segmentation algorithm with ground-truth, which is based on computing the deviation of segmentation results from the reference segmentation. Four different metrics based on classification pixels, edges, relative foreground area and relative position respectively are combined to address the spatial accuracy. Temporal coherency is evaluated by utilizing the difference of spatial accuracy between successive frames. The experimental results show the feasibility of our approach. Moreover, it is computationally more efficient than previous methods. It can be applied to provide an offline ranking among different segmentation algorithms and to optimally set the parameters for a given algorithm.

关键词： video object segmentation performance evaluation MPEG-4.

维普期刊数据库